Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variations of the word "hollow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vak
    -0.16
    sar
    -0.16
    sik
    -0.15
    uro
    -0.15
    nem
    -0.15
    enario
    -0.15
    asto
    -0.15
    ائÙĤ
    -0.15
    jom
    -0.14
    urga
    -0.14
    POSITIVE LOGITS
    ed
    0.25
    oods
    0.20
    icz
    0.20
    ood
    0.20
    idge
    0.18
    ry
    0.18
    czy
    0.18
    est
    0.17
    itz
    0.17
    ays
    0.17
    Act Density 0.024%

    No Known Activations